VccmDataset
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Contradictory-style Generation | VccmDataset | MOS-SA4.71 | 168 | |
| Emotion Transfer | VccmDataset (test) | Accuracy100 | 21 | |
| Text-to-Speech | VccmDataset (test A) | Pitch0.954 | 6 | |
| Style-controllable Speech Synthesis | VccmDataset C (test) | Pitch0.85 | 6 | |
| Text-to-Speech | VccmDataset set D (test) | Metric- | 0 |
Showing 5 of 5 rows